© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 333
    Prev
    Next
    INDEX
    Explanations

    interface, application, narrower, early, editable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    whatsapp
    1.32
    ukk
    1.30
    ukkh
    1.25
     উন্নয়নে
    1.21
    »:
    1.20
    suk
    1.20
    ilib
    1.20
    intu
    1.20
    aspid
    1.18
    esu
    1.18
    POSITIVE LOGITS
    чей
    1.14
     someplace
    1.09
     ("
    1.06
    。。。
    1.04
     (
    1.00
    的一部分
    1.00
     combo
    0.99
     κάπο
    0.99
     FYI
    0.98
    。"
    0.97
    Activations Density 0.000%

    No Known Activations